A method and system for intelligent analysis of the operating status of communication equipment

Abstract

This invention relates to the field of communication equipment analysis, specifically to an intelligent analysis method and system for the operational status of communication equipment. The method includes the following steps: collecting operational data from key functional units of the target communication equipment; organizing the operational data of each unit according to the sampling time sequence to construct a unit status dataset; analyzing the communication equipment based on the key functional units, constructing a power consumption chain stack structure, and attaching structural fragment labels to the power consumption chain stack structure based on the unit status dataset; dividing the power consumption chain stack structure into sliding windows based on the structural fragment labels to extract behavioral micro-blocks; analyzing adjacent behavioral micro-blocks and identifying the status of the communication equipment; analyzing the communication equipment based on the behavioral micro-blocks, constructing a disturbance synchronization matrix, identifying coupling resonance relationships, constructing a structural health map, and generating corresponding operational strain strategies for the communication equipment. This invention can improve the stability and intelligent management level of communication equipment.

Description

Technical Field

[0001] This invention relates to the field of communication equipment analysis, and specifically to an intelligent analysis method and system for the operating status of communication equipment. Background Technology

[0002] As the complexity of communication base station equipment continues to increase, communication systems place higher demands on the real-time analysis and intelligent sensing capabilities of key equipment operation status. Especially in application scenarios such as 5G communication, high-density base station deployment, and edge computing, communication equipment integrates multiple key functional units, such as radio frequency transmission channels, power amplification modules, and main control processing units.

[0003] Chinese patent CN119276718A discloses a method for online monitoring and maintenance of communication equipment operation, which is used in conjunction with normal on-site inspections. The method includes a central monitoring platform, which is equipped with a monitoring system and an execution module. The monitoring system contains a device list. The central monitoring platform allocates different online monitoring strategies according to the device category and under different network load conditions. The execution module matches the online monitoring strategies with the operation and maintenance plan.

[0004] Due to long-term operation, high-frequency load changes, and spatial structure coupling effects, the operating states of various units within communication equipment exhibit obvious nonlinear fluctuation characteristics, especially in terms of power consumption distribution, fluctuation frequency, and energy consumption abrupt changes, showing significant time-series coupling characteristics. Existing technologies struggle to identify potential coupling relationships, construct dynamic analysis models oriented towards structural health, and effectively identify disturbance synchronization and resonance risks between communication equipment channels. These are problems we need to solve. Summary of the Invention

[0005] The purpose of this invention is to address the problems existing in the background technology by proposing an intelligent analysis method and system for the operating status of communication equipment.

[0006] The technical solution of this invention: A method for intelligent analysis of the operating status of communication equipment, comprising the following steps:

[0007] S1. Collect the operating data of each key functional unit in the target communication device, organize the operating data of each unit according to the sampling time series, and construct the unit status dataset;

[0008] S2. Analyze the communication equipment based on key functional units, construct a power consumption chain stack structure, and add structural segment labels to the power consumption chain stack structure in combination with the unit state dataset.

[0009] S3. Based on structural fragment labels, the power consumption chain stack structure is divided into sliding windows to extract behavioral micro-blocks; adjacent behavioral micro-blocks are analyzed, and the status of the communication device is identified.

[0010] S4. Analyze the communication device based on the behavioral micro-blocks, construct a perturbation synchronization matrix, identify the coupled resonance relationship based on the state of the communication device, construct a structural health map, and generate an operation strain strategy for the corresponding communication device.

[0011] Preferably, the process of collecting the operation data of each key functional unit in the target communication device and sorting the operation data of each unit according to the sampling time series to construct a unit state data set includes:

[0012] Collect the operation data of each key functional unit in the target communication device. The key functional units include a radio frequency transmission channel, a main control processing unit, a power amplification unit, and a device state control unit; the operation data includes power consumption value, current, voltage, chip temperature, and output power; sort the operation data of each key functional unit in chronological order to construct a unit state data set. Each record in the unit state data set includes a unit identifier, a sampling timestamp, and an operation index value; the operation index values include average power consumption, instantaneous change rate of power consumption, task processing delay value, and communication anomaly count index; construct a structured index field for the unit state data set. The structured index field includes a unit category index, a time segment index, and an anomaly response flag bit.

[0013] Preferably, the process of analyzing the communication device based on the key functional units and constructing a power consumption chain stack structure includes:

[0014] Set the sampling period; collect the power consumption values of each radio frequency transmission channel of the target communication device in the communication base station within multiple consecutive sampling periods, combine the communication power consumption data of all radio frequency transmission channels within the same sampling period according to the channel arrangement structure, and generate a layer of channel power consumption distribution status;

[0015] Stack the channel power consumption distribution status within multiple sampling periods in chronological order to construct a power consumption chain stack structure with multiple time slices. The power consumption chain stack structure is a chained structure composed of several consecutive time slices. Each time slice corresponds to a channel power consumption distribution status. Use the position of each channel in each time slice as a communication node in the power consumption chain stack structure. The communication node contains a node field, and the node field includes a channel number, a power consumption value, a historical offset value, and a fluctuation frequency.

[0016] Preferably, the process of attaching a structural fragment label to the power consumption chain stack structure in combination with the unit state data set is:

[0017] Based on the power consumption chain stack structure, communication nodes containing abnormal response flags are filtered out, and the channel number, power consumption index of the abnormality trigger, time slice number of the abnormality and its key functional unit are extracted. The power consumption index includes historical offset value, fluctuation frequency, average power consumption and instantaneous power consumption change rate. Structural segment tags are constructed and attached to the corresponding time slice.

[0018] Preferably, the power consumption stack structure is divided into sliding window segments based on structural fragment labels to extract behavioral micro-blocks; the process of analyzing adjacent behavioral micro-blocks includes:

[0019] Based on the channel number, time slice number, and power consumption index of the structural fragment label, a two-dimensional power consumption matrix is ​​constructed, with the channel number as the column index, the time slice number as the row index, and the matrix elements as power consumption indices. A sliding window is used to identify multiple communication nodes that are adjacent in time and channel dimensions and have the same power consumption index when anomalies occur, dividing them into the smallest response behavior units to obtain behavior micro-blocks. The sliding window size is set with a sliding sampling period and a sliding step size. Based on each behavior micro-block, the Shannon entropy of the power consumption distribution within the behavior micro-block is statistically calculated. The local standard deviation of the power consumption values ​​within each behavior micro-block is calculated. The relative entropy change rate between two adjacent micro-blocks is calculated sequentially.

[0020] Preferably, the process of identifying the status of a communication device includes:

[0021] Analyzing the power consumption stack structure, when a decrease in the relative entropy change rate and a decrease in the local standard deviation occur in a continuous behavioral micro-block, it is determined that the channel behavior tends to freeze, and the energy consumption state becomes simple and predictable. The behavioral micro-block is recorded as the "entropy convergence" state. When a behavioral micro-block shows a rebound in the relative entropy change rate and an increase in the local standard deviation, it indicates that the behavior inside the channel is showing an unstable fluctuation trend. The behavioral micro-block is recorded as the "noise enhancement" state. If the Shannon entropy value of a certain micro-block exceeds the preset entropy threshold and the local standard deviation abnormally increases, it is determined that the channel is in a power consumption behavior mutation state. The behavioral micro-block is recorded as the "power consumption anomaly" state.

[0022] When the state of the radio frequency transmission channel of a communication device in multiple consecutive behavioral micro-blocks occurs in the order of entropy convergence, noise enhancement, and power consumption anomaly, the communication device is recorded as a "behavioral crushing" state; otherwise, it is recorded as a "behavioral stable" state.

[0023] Preferably, the process of analyzing communication devices based on behavioral micro-blocks, constructing a perturbation synchronization matrix, identifying coupling resonance relationships based on the state of the communication devices, constructing a structural health map, and generating corresponding operational strain strategies for the communication devices includes:

[0024] Based on the behavioral micro-blocks obtained from each RF transmission channel, a perturbation synchronization matrix is ​​constructed. The perturbation synchronization matrix is ​​used to represent the cooperative relationship between each RF transmission channel in terms of timing fluctuation characteristics. The cooperative relationship refers to the fact that within the same sampling window, multiple RF transmission channels synchronously exceed the preset fluctuation threshold in power consumption fluctuation rate and change in the same direction. Boolean flags are used to record whether there is a high-frequency cooperative mutation relationship, and a perturbation coupling structure between channel pairs is constructed.

[0025] When an RF transmission channel is identified as being in a "behavioral crush" state, it is detected whether adjacent RF transmission channels exhibit a sudden increase in power consumption or enhanced noise disturbance within the time window of the behavioral micro-block corresponding to the "behavioral crush" state. The range of the time window is... Where T is the center time point of the behavioral micro-block identified as being in a "behavioral crush" state by the radio frequency transmission channel. The set time window threshold is used; if it exists, it is determined that there is a coupling resonance relationship between the radio frequency transmission channels, and they are marked as "resonance chain" channel pairs in the perturbation synchronization matrix, and the corresponding communication nodes are marked as coupling resonance nodes; combining the power consumption chain stack structure, "behavioral crushing" state and coupling resonance relationship, a structural health map of the communication equipment is generated. The structural health map has each radio frequency transmission channel as a node and the coupling resonance relationship as an edge; based on the structural health map, an operational strain strategy is generated, which includes channel tuning limiting strategy, power supply limiting strategy, backup redundancy suggestion and fault tolerance update mechanism.

[0026] This invention also discloses an intelligent analysis system for the operating status of communication equipment, including a management center, which is communicatively connected to a data acquisition module, a structure construction module, a status analysis module, and an operation management module.

[0027] The data acquisition module is used to collect the operating data of each key functional unit in the target communication device, organize the operating data of each unit according to the sampling time series, and construct the unit status dataset;

[0028] The structure building module is used to analyze communication devices based on key functional units, build a power consumption chain stack structure, and add structural fragment labels to the power consumption chain stack structure in combination with the unit state dataset.

[0029] The state analysis module is used to divide the power consumption chain stack structure into sliding windows based on structural fragment labels, extract behavioral micro-blocks, analyze adjacent behavioral micro-blocks, and identify the state of the communication device.

[0030] The operation management module is used to analyze communication devices based on behavioral micro-blocks, construct a disturbance synchronization matrix, identify coupling resonance relationships based on the state of communication devices, construct a structural health map, and generate corresponding operation strain strategies for communication devices.

[0031] Compared with the prior art, the above technical solution of the present invention has the following beneficial technical effects: By constructing a sequence of behavioral micro-blocks based on a power consumption chain stack structure and introducing a joint analysis mechanism of Shannon entropy and relative entropy change rate, it is possible to continuously monitor the "entropy convergence-noise enhancement-power consumption anomaly" collapse evolution trend during the operation of communication devices, and accurately identify the early abnormal behavior state without relying on fixed thresholds or static indicators; By constructing a perturbation synchrony matrix based on behavioral micro-blocks, identifying channel pairs with high-frequency co-mutation relationships, and forming a resonance chain analysis model in combination with a structural health map, it is possible to effectively mine the coupled abnormal propagation paths between internal channels of the device, enhance the response ability to chain collapse risks, and support the regulation of the operating state of communication devices and the generation of dynamic response strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a flowchart of an embodiment proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] Embodiment 1, as Figure 1 shown, an intelligent analysis method for the operating state of a communication device proposed by the present invention includes the following steps:

[0034] S1. Collect the operation data of each key functional unit in the target communication device, sort the operation data of each unit according to the sampling time series, and construct a unit state data set;

[0035] S2. Analyze the communication device based on the key functional units, construct a power consumption chain stack structure, and attach structure fragment labels to the power consumption chain stack structure in combination with the unit state data set;

[0036] S3. Divide the power consumption chain stack structure by a sliding window based on the structure fragment labels, extract behavioral micro-blocks; analyze adjacent behavioral micro-blocks and identify the state of the communication device;

[0037] S4. Analyze the communication device based on the behavioral micro-blocks, construct a perturbation synchrony matrix, identify the coupled resonance relationship based on the state of the communication device, construct a structural health map, and generate an operation response strategy for the corresponding communication device.

[0038] It should be further noted that in the specific implementation process, the process of collecting the operation data of each key functional unit in the target communication device, sorting the operation data of each unit according to the sampling time series, and constructing a unit state data set is:

[0039] Collect the operation data of each key functional unit in the target communication device. The key functional units include a radio frequency transmission channel, a main control processing unit, a power amplification unit, and a device status control unit. The operation data includes power consumption value, current, voltage, chip temperature, and output power. Sort the operation data of each key functional unit in chronological order to construct a unit status data set. Each record in the unit status data set includes a unit identifier, a sampling timestamp, and an operation metric value. The unit identifier refers to the identifiers corresponding to the radio frequency transmission channel, the main control processing unit, the power amplification unit, and the device status control unit respectively. The operation metric value includes average power consumption, instantaneous power consumption change rate, task processing delay value, and communication anomaly count metric.

[0040] Construct a structured index field for the unit status data set. The structured index field includes a unit category index, a time segment index, and an anomaly response flag bit. The unit category index is stratified according to the unit function type. For example, the data of all radio frequency channels is divided into the first layer, and the data of the main control processing unit is divided into the second layer. The time segment index refers to dividing the unit status data set into several consecutive time periods, and each time slice contains the operation data of multiple units in the corresponding period. The anomaly response flag bit refers to setting a Boolean flag bit in the unit status data set. If abnormal jumps, intermittent fluctuations, or error accumulation exceeding the limit are detected in the operation data, the corresponding flag bit is set to 1, otherwise it is 0.

[0041] It should be further noted that in the specific implementation process, when analyzing the communication device based on the key functional units and constructing a power consumption chain stack structure, the process of attaching structure fragment tags to the power consumption chain stack structure in combination with the unit status data set is as follows:

[0042] Set the sampling period, and the sampling period is a fixed time interval. Collect the power consumption values of each radio frequency transmission channel of the target communication device in the communication base station within multiple consecutive sampling periods. Combine the communication power consumption data of all radio frequency transmission channels in the same sampling period according to the channel arrangement structure to generate a channel power consumption distribution state at one layer. The channel power consumption distribution state refers to the spatial distribution result of the power consumption values of each radio frequency transmission channel in the communication device within the sampling period. The power consumption values are arranged in channel order to form a channel power consumption vector, and each element in the channel power consumption vector represents the measured power consumption value of the corresponding radio frequency transmission channel in the corresponding sampling period.

[0043] Stack the channel power consumption distribution states within multiple sampling periods in chronological order to construct a power consumption chain stack structure with multiple time slices. Take the sampling period as the unit, and collect the communication power consumption data of all radio frequency transmission channels at the same moment to form a power consumption snapshot, which is used as a time slice. [[ID=*]] [[ID=*]]

[0044] The power consumption chain stack structure is a chain structure composed of several consecutive time slices in sequence. Each time slice corresponds to a channel power consumption distribution state. The position of each channel in each time slice is used as a communication node in the power consumption chain stack structure. The communication node contains node fields, and the node fields include a channel number, a power consumption value, a historical offset value, and a fluctuation frequency. The power consumption value refers to the actual sampled power consumption value of the radio frequency transmission channel. The historical offset value refers to the power consumption difference of the corresponding radio frequency transmission channel between the previous sampling period and the current sampling period. The fluctuation frequency is obtained by counting the number of power consumption mutations of the corresponding radio frequency transmission channel within the time slice. The power consumption mutation refers to an event where, within consecutive sampling periods, when the change amplitude of the power consumption value of the radio frequency transmission channel exceeds a preset change threshold and the change duration exceeds a preset minimum continuous window length, it is recorded as a power consumption mutation event.

[0045] Based on the power consumption chain stack structure, screen the communication nodes containing the abnormal response flag bit, extract the channel number, the power consumption index triggered by the abnormality, the time slice number where the abnormality is located, and its affiliated key functional unit of the corresponding communication node, construct a structure fragment label, and attach it to the corresponding time slice. The structure fragment label is used to identify the device response behavior characteristics of the corresponding time slice under the channel power consumption state.

[0046] It should be further noted that in the specific implementation process, based on the structure fragment label, divide the power consumption chain stack structure by a sliding window, and extract behavior micro-blocks. The process of analyzing adjacent behavior micro-blocks and identifying the state of the communication device is as follows:

[0047] Denote the constructed power consumption chain stack structure as , where represents the power consumption value of the radio frequency transmission channel at time point t; based on the power consumption chain stack structure of each channel, use the sliding window method to perform continuous segmentation to obtain multiple behavior micro-blocks of equal length , where n represents the total number of behavior micro-blocks obtained by division, represents the nth behavior micro-block; the size of the sliding window is set with a sliding sampling period and a sliding step length;

[0048] Based on each behavior micro-block, statistically calculate the Shannon entropy of the power consumption distribution within the behavior micro-block. The calculation formula of the Shannon entropy is: , where represents the normalized probability that the power consumption value falls within the power consumption distribution interval of the ith behavior micro-block within the current sliding window, reflecting the relative occurrence frequency of the power consumption level; it is obtained by normalizing the statistical histogram within the window; the Shannon entropy is used to measure the dispersion degree of the power consumption values within the behavior micro-block; calculate the local standard deviation of the power consumption values within each behavior micro-block The local standard deviation is used to reflect the intensity of energy consumption fluctuations;

[0049] The relative entropy change rate between two adjacent micro-blocks is calculated sequentially. This relative entropy change rate measures the change in the distribution structure of the power consumption stack within a locally continuous micro-block. The relative entropy change rate is a commonly used distribution difference index in existing information theory, and its calculation method can be based on known formulas. ,in and ε represents the Shannon entropy values ​​of two adjacent micro-blocks, respectively, and ε is a minimal constant to prevent the denominator from being zero;

[0050] Analyzing the power consumption stack structure, when a decrease in the relative entropy change rate and a decrease in the local standard deviation occur in a continuous behavioral micro-block, it is determined that the channel behavior tends to freeze, and the energy consumption state becomes simple and predictable. The behavioral micro-block is recorded as the "entropy convergence" state. When a behavioral micro-block shows a rebound in the relative entropy change rate and an increase in the local standard deviation, it indicates that the behavior inside the channel is showing an unstable fluctuation trend. The behavioral micro-block is recorded as the "noise enhancement" state. If the Shannon entropy value of a certain micro-block exceeds the preset entropy threshold and the local standard deviation abnormally increases, it is determined that the channel is in a power consumption behavior mutation state. The behavioral micro-block is recorded as the "power consumption anomaly" state.

[0051] When the state of the radio frequency transmission channel of a communication device in multiple consecutive behavioral micro-blocks occurs in the order of entropy convergence, noise enhancement, and power consumption anomaly, the communication device is recorded as a "behavioral crushing" state; otherwise, it is recorded as a "behavioral stable" state.

[0052] It should be further explained that, in the specific implementation process, the process of analyzing communication devices based on behavioral micro-blocks, constructing a disturbance synchronization matrix, identifying coupling resonance relationships based on the state of the communication devices, constructing a structural health map, and generating corresponding operational response strategies for the communication devices is as follows:

[0053] Based on the behavioral micro-blocks obtained from each radio frequency transmission channel, a perturbation synchronization matrix is ​​constructed. The perturbation synchronization matrix is ​​used to represent the cooperative relationship between each radio frequency transmission channel in terms of timing fluctuation characteristics. The cooperative relationship refers to the fact that within the same sampling window, multiple radio frequency transmission channels synchronously exceed a preset fluctuation threshold in power consumption fluctuation rate and change in the same direction. Boolean flags are used to record whether there is a high-frequency cooperative mutation relationship, and a perturbation coupling structure between channel pairs is constructed.

[0054] When an RF transmit channel is identified as being in a "behavioral crush" state, it is detected whether adjacent RF transmit channels exhibit a sudden increase in power consumption or enhanced noise disturbance within a time window corresponding to the "behavioral crush" state. The range of this time window is... Where T is the center time point of the behavioral micro-block identified as being in a "behavioral crush" state by the radio frequency transmission channel. The set time window threshold; if it exists, it is determined that the radio frequency transmission channel pair has a coupling resonance relationship, and it is marked as a "resonance chain" channel pair in the disturbance synchronization matrix, and the corresponding communication node is marked as a coupling resonance node;

[0055] By combining the power consumption stack structure, the "behavioral crush" state, and the coupling resonance relationship, a structural health map of the communication device is generated. The structural health map uses each radio frequency transmission channel as a node and the coupling resonance relationship as an edge.

[0056] Operational response strategies are generated based on structural health maps. These strategies guide communication equipment in resource adjustments and functional redundancy responses to potential crush and resonance risks. The operational response strategies include channel limiting strategies, power supply limiting strategies, backup redundancy recommendations, and fault-tolerant update mechanisms. Specifically, the channel limiting strategy dynamically lowers the transmit power limit or communication duty cycle of channels in a "behavioral crush" state or on a resonance chain to avoid load accumulation effects. The power supply limiting strategy temporarily limits current or adjusts power supply priority for high-risk channels based on channel fluctuation frequency and power consumption transition trends. The backup redundancy recommendation suggests adding standby channels to channel combinations with frequent resonance paths in the structural health map to build an operational redundancy mechanism. The fault-tolerant update mechanism updates the sliding window width when disturbance coupling structures repeatedly occur and continuously affect multiple functional units, adapting to the volatility of the current operating environment.

[0057] Example 2: The intelligent analysis system for the operating status of communication equipment proposed in this invention is applied to the intelligent analysis method for the operating status of communication equipment described in Example 1. Specifically, it includes a management center, which is communicatively connected to a data acquisition module, a structure construction module, a status analysis module, and an operation management module.

[0058] The data acquisition module is used to collect the operating data of each key functional unit in the target communication device, organize the operating data of each unit according to the sampling time series, and construct the unit status dataset;

[0059] The structure building module is used to analyze communication devices based on key functional units, build a power consumption chain stack structure, and add structural fragment labels to the power consumption chain stack structure in combination with the unit state dataset.

[0060] The state analysis module is used to divide the power consumption chain stack structure into sliding windows based on structural fragment labels, extract behavioral micro-blocks, analyze adjacent behavioral micro-blocks, and identify the state of the communication device.

[0061] The operation management module is used to analyze communication devices based on behavioral micro-blocks, construct a disturbance synchronization matrix, identify coupling resonance relationships based on the state of communication devices, construct a structural health map, and generate corresponding operation strain strategies for communication devices.

[0062] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited thereto. Various changes can be made within the scope of knowledge possessed by those skilled in the art without departing from the spirit of the present invention.

Claims

1. A method for intelligent analysis of the operating status of communication equipment, characterized in that, Includes the following steps: S1. Collect the operating data of each key functional unit in the target communication device, organize the operating data of each unit according to the sampling time series, and construct the unit status dataset; S2. Analyze the communication equipment based on key functional units, construct a power consumption chain stack structure, and add structural segment labels to the power consumption chain stack structure in combination with the unit state dataset. S3. Based on structural fragment labels, the power consumption chain stack structure is divided into sliding windows to extract behavioral micro-blocks; adjacent behavioral micro-blocks are analyzed, and the status of the communication device is identified. S4. Analyze communication devices based on behavioral micro-blocks, construct a disturbance synchronization matrix, identify coupling resonance relationships based on the state of communication devices, construct a structural health map, and generate corresponding operational strain strategies for communication devices. The process of analyzing communication devices based on key functional units and constructing a power consumption stack structure includes: Set the sampling period; collect the power consumption values ​​of each radio frequency transmission channel of the target communication device in the communication base station in multiple consecutive sampling periods, and combine the communication power consumption data of all radio frequency transmission channels in the same sampling period according to the channel arrangement structure to generate a layer of channel power consumption distribution status; The power consumption distribution states of the channels in multiple sampling periods are superimposed in time order to construct a power consumption chain stack structure with multiple time slices. The power consumption chain stack structure is a chain structure composed of several consecutive time slices. Each time slice corresponds to the power consumption distribution state of a channel. The position of each channel in each time slice is used as a communication node in the power consumption chain stack structure. The communication node contains a node field, which includes the channel number, power consumption value, historical offset value and fluctuation frequency. The process of adding structural segment labels to the power chain stack structure based on the cell state dataset is as follows: Based on the power consumption chain stack structure, the communication nodes containing abnormal response flag bits are filtered, and the channel number, power consumption index of abnormal trigger, time slice number of abnormality and its key functional unit are extracted. The power consumption index includes historical offset value, fluctuation frequency, average power consumption and instantaneous power consumption change rate. The structural segment label is constructed and attached to the corresponding time slice. The power consumption stack structure is divided into sliding window segments based on structural fragment labels to extract behavioral micro-blocks; the process of analyzing adjacent behavioral micro-blocks includes: Based on the channel number, time slice number, and power consumption index of the structural fragment labels, a two-dimensional power consumption matrix is ​​constructed, with the channel number as the column index, the time slice number as the row index, and the matrix elements as power consumption indices. A sliding window is used to identify multiple communication nodes that are adjacent in both time and channel dimensions and have the same power consumption index when anomalies are triggered. These nodes are then divided into the smallest response behavior units, resulting in behavior micro-blocks. The sliding window size is configured with a sliding sampling period and a sliding step size. Based on each behavior micro-block, the Shannon entropy of the power consumption distribution within the behavior micro-block is statistically calculated. The local standard deviation of the power consumption values ​​within each behavior micro-block is calculated. Finally, the relative entropy change rate between two adjacent micro-blocks is calculated sequentially. The process of identifying the status of communication devices includes: Analyzing the power consumption stack structure, when the relative entropy change rate decreases and the local standard deviation decreases in a continuous micro-block, it is determined that the channel behavior tends to freeze, and the energy consumption state becomes simple and predictable. The micro-block is then recorded as the "entropy convergence" state. When the relative entropy change rate of a micro-block increases and the local standard deviation rises, it indicates that the behavior inside the channel is showing an unstable fluctuation trend. The micro-block is then recorded as the "noise enhancement" state. If the Shannon entropy value of a certain micro-block exceeds a preset entropy threshold and the local standard deviation abnormally increases, it is determined that the channel is in a power consumption behavior mutation state. The micro-block is then recorded as the "power consumption anomaly" state. When the state of the radio frequency transmission channel of a communication device in multiple consecutive behavioral micro-blocks occurs in the order of entropy convergence, noise enhancement, and power consumption anomaly, the communication device is recorded as a "behavioral crushing" state; otherwise, the communication device is recorded as a "behavioral stable" state. The process of analyzing communication devices based on behavioral micro-blocks, constructing a perturbation synchronization matrix, identifying coupling resonance relationships based on the state of the communication devices, constructing a structural health map, and generating corresponding operational response strategies for the communication devices includes: Based on the behavioral micro-blocks obtained from each RF transmission channel, a perturbation synchronization matrix is ​​constructed. The perturbation synchronization matrix is ​​used to represent the cooperative relationship between each RF transmission channel in terms of timing fluctuation characteristics. The cooperative relationship refers to the fact that within the same sampling window, multiple RF transmission channels synchronously exceed the preset fluctuation threshold in power consumption fluctuation rate and change in the same direction. Boolean flags are used to record whether there is a high-frequency cooperative mutation relationship, and a perturbation coupling structure between channel pairs is constructed. When an RF transmit channel is identified as being in a "behavioral crush" state, it is detected whether adjacent RF transmit channels exhibit a sudden increase in power consumption or enhanced noise disturbance within the time window of the behavioral micro-block corresponding to the "behavioral crush" state. The range of the time window is... Where T is the center time point of the behavioral micro-block identified as being in a "behavioral crush" state by the radio frequency transmission channel. The set time window threshold is used; if it exists, it is determined that there is a coupling resonance relationship between the radio frequency transmission channels, and they are marked as "resonance chain" channel pairs in the perturbation synchronization matrix, and the corresponding communication nodes are marked as coupling resonance nodes; combining the power consumption stack structure, "behavioral crush" state and coupling resonance relationship, a structural health map of the communication equipment is generated. The structural health map has each radio frequency transmission channel as a node and the coupling resonance relationship as an edge; based on the structural health map, an operational strain strategy is generated, which includes channel tuning limiting strategy, power supply limiting strategy, backup redundancy suggestion and fault tolerance update mechanism.

2. The intelligent analysis method for the operating status of communication equipment according to claim 1, characterized in that, The process of collecting operational data from key functional units in the target communication device, organizing the operational data of each unit according to the sampling time series, and constructing a unit status dataset includes: The system collects operational data from key functional units within the target communication device. These key functional units include the RF transmission channel, main control processing unit, power amplification unit, and device status control unit. Operational data includes power consumption, current, voltage, chip temperature, and output power. The operational data for each key functional unit is organized chronologically to construct a unit status dataset. Each record in the unit status dataset includes a unit identifier, a sampling timestamp, and operational indicator values. Operational indicator values ​​include average power consumption, instantaneous power consumption change rate, task processing latency, and communication anomaly count. A structured index field is constructed for the unit status dataset, including a unit category index, a time segment index, and an anomaly response flag.

3. A communication equipment operation status intelligent analysis system, specifically applied to the communication equipment operation status intelligent analysis method according to any one of claims 1 to 2, comprising a management center, characterized in that, The management center communication connection includes a data acquisition module, a structure construction module, a status analysis module, and an operation management module. The data acquisition module is used to collect the operating data of each key functional unit in the target communication device, organize the operating data of each unit according to the sampling time series, and construct the unit status dataset; The structure building module is used to analyze communication devices based on key functional units, build a power consumption chain stack structure, and add structural fragment labels to the power consumption chain stack structure in combination with the unit state dataset. The state analysis module is used to divide the power consumption chain stack structure into sliding windows based on structural fragment labels, extract behavioral micro-blocks, analyze adjacent behavioral micro-blocks, and identify the state of the communication device. The operation management module is used to analyze communication devices based on behavioral micro-blocks, construct a disturbance synchronization matrix, identify coupling resonance relationships based on the state of communication devices, construct a structural health map, and generate corresponding operation strain strategies for communication devices.

Images